Lightweighting Techniques to Improve Real-time Recognition Performance of License Plate Using IP Cameras with Low-end NPUs 


Vol. 13,  No. 11, pp. 645-653, Nov.  2024
https://doi.org/10.3745/TKIPS.2024.13.11.645


PDF
  Abstract

This paper proposes a lightweight method to improve the performance of real-time vehicle number recognition on low-specification embedded devices, to solve the problem of increasing physical space and cost due to the expansion of the vehicle number recognition market. The proposed method is based on a lightweight CNN model and uses techniques such as image preprocessing, hyperparameter optimization, activation function optimization, and quantization to simultaneously improve recognition accuracy and speed. Experiments show that, in the case of the SSD-lite model, image preprocessing with Shi-Tomasi corner detection, the application of ReLU4 as the activation function, and quantization resulted in an mAP@.5 of 0.94, which is an accuracy improvement of more than 10%, and a recognition time of 10.9 ms, which is a speed improvement of more than 10%. In addition, the proposed method meets real-time requirements (FPS ≥ 30) with minimal loss of accuracy and a speed improvement of about 10% on IP cameras using the EN675 SoC of EYENIX, an edge device with an NPU performance of 1.2 TOPS.

  Statistics
  Cite this article

[IEEE Style]

J. Han and G. Kim, "Lightweighting Techniques to Improve Real-time Recognition Performance of License Plate Using IP Cameras with Low-end NPUs," The Transactions of the Korea Information Processing Society, vol. 13, no. 11, pp. 645-653, 2024. DOI: https://doi.org/10.3745/TKIPS.2024.13.11.645.

[ACM Style]

Ju-Hwan Han and Gye-Young Kim. 2024. Lightweighting Techniques to Improve Real-time Recognition Performance of License Plate Using IP Cameras with Low-end NPUs. The Transactions of the Korea Information Processing Society, 13, 11, (2024), 645-653. DOI: https://doi.org/10.3745/TKIPS.2024.13.11.645.

Forms

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)

Old Journals

Indexing

All publications of TKIPS is indexed in DOI, EBSCO, Google Scholar, Crossref, and CrossCheck.

TKIPS is also selected as the Journal for Accreditation by NRF (National Research Foundation of Korea).

Related Journals